The controller raises what the watchman says stopped moving, and takes a machine's silence from its presence (issue 1156)

cmd/mesh-controller/stuck_probe_test.go

@@ -0,0 +1,108 @@
+package main
+
+import (
+	"strings"
+	"testing"
+	"time"
+
+	sdkdelivery "git.novox.be/novox/mesh-sdk/go/delivery"
+
+	"github.com/novox/mesh-controller/internal/conditions"
+	"github.com/novox/mesh-controller/internal/link"
+)
+
+func aStuckKey(t *testing.T, bucket, key string) string {
+	t.Helper()
+	k, err := sdkdelivery.StuckKey(bucket, key)
+	if err != nil {
+		t.Fatal(err)
+	}
+	return k
+}
+
+// 1156/AC1: each not-moved stuck key that is not a node's presence is an observation of the delivery scope, kind stuck,
+// naming the key and what it waited for; a moved key raises nothing, so its condition clears.
+func TestEachStuckKeyThatHasNotMovedIsAConditionOfTheDeliveryScope(t *testing.T) { // 1156/AC1
+	since := time.Date(2026, 10, 18, 19, 0, 0, 0, time.UTC)
+	pulse := aStuckKey(t, sdkdelivery.PulseBucket, "x")
+	moved := aStuckKey(t, sdkdelivery.HaveBucket, "ace.zsh")
+	node := aStuckKey(t, sdkdelivery.PresenceBucket, "ace")
+	part := aStuckKey(t, sdkdelivery.PresenceBucket, "part.mesh-controller.one")
+	entries := map[string]sdkdelivery.Stuck{
+		pulse: {Bucket: sdkdelivery.PulseBucket, Key: "x", Waited: "the build of zsh to be answered", Since: since},
+		moved: {Bucket: sdkdelivery.HaveBucket, Key: "ace.zsh", Waited: "a want", Since: since, Moved: true},
+		node:  {Bucket: sdkdelivery.PresenceBucket, Key: "ace", Waited: "its return", Since: since},
+		part:  {Bucket: sdkdelivery.PresenceBucket, Key: "part.mesh-controller.one", Waited: "its return", Since: since},
+	}
+	got := stuckObservations(entries)
+	if len(got) != 2 {
+		t.Fatalf("observations %+v, want the pulse key and the part's presence", got)
+	}
+	byID := map[string]conditions.Observation{}
+	for _, o := range got {
+		if o.Scope != conditions.ScopeDelivery || o.Kind != kindStuck {
+			t.Errorf("%+v is not a stuck condition of the delivery scope", o)
+		}
+		byID[o.ID] = o
+	}
+	o, ok := byID[pulse]
+	if !ok || !strings.Contains(o.Summary, pulse) || !strings.Contains(o.Summary, "the build of zsh to be answered") {
+		t.Fatalf("the condition does not name the key and what it waited for: %+v", got)
+	}
+	if _, ok := byID[part]; !ok {
+		t.Errorf("a part's presence is left out: %v", byID)
+	}
+	// Moved again: the same key, written as moved, raises nothing.
+	entries[pulse] = sdkdelivery.Stuck{Bucket: sdkdelivery.PulseBucket, Key: "x", Since: since, Moved: true}
+	if got := stuckObservations(entries); len(got) != 1 {
+		t.Fatalf("a moved key still raises: %+v", got)
+	}
+}
+
+func aMachineHeardAt(now time.Time, ago time.Duration) machineFacts {
+	return machineFacts{name: "laptop", lastHeard: now.Add(-ago), every: time.Minute}
+}
+
+// 1156/AC2: a node's stuck presence key not moved makes the machine silent, unless it sleeps; moved, it is heard; no
+// timer is armed (the verdict is the key's, whatever the time of the last word).
+func TestAStuckPresenceKeyIsTheSilentVerdict(t *testing.T) { // 1156/AC2
+	now := time.Now()
+	f := calm(now)
+	f.machines = append(f.machines, aMachineHeardAt(now, 10*time.Second))
+	notMoved := sdkdelivery.Stuck{Bucket: sdkdelivery.PresenceBucket, Key: "laptop", Waited: "its return", Since: now.Add(-3 * time.Minute)}
+	applyPresence(&f.machines[1], &notMoved, now.Add(-3*time.Minute))
+	got := watchHeartbeats(f)
+	if len(got) != 1 || got[0].Machine != "laptop" || got[0].Kind != "silent" {
+		t.Fatalf("a presence key not moved: %+v", got)
+	}
+	// Asleep: not silent.
+	f.machines[1].power = link.PowerState{State: "sleeping", At: now.Add(-time.Hour)}
+	if got := watchHeartbeats(f); len(got) != 0 {
+		t.Fatalf("a sleeping machine raised %+v", got)
+	}
+	// Moved: heard, whatever the store's last word says.
+	f.machines[1].power = link.PowerState{}
+	f.machines[1].lastHeard = now.Add(-2 * time.Hour)
+	moved := notMoved
+	moved.Moved = true
+	applyPresence(&f.machines[1], &moved, now.Add(-time.Minute))
+	if got := watchHeartbeats(f); len(got) != 0 {
+		t.Fatalf("a presence key that moved raised %+v", got)
+	}
+}
+
+// 1156/AC3: a machine's last heard is the presence key's entry time when there is one, and last_seen when there is none.
+func TestLastHeardIsThePresenceKeysTimeWhenThereIsOne(t *testing.T) { // 1156/AC3
+	now := time.Now()
+	seen := now.Add(-time.Hour)
+	m := machineFacts{name: "laptop", lastHeard: seen}
+	applyPresence(&m, nil, time.Time{})
+	if !m.lastHeard.Equal(seen) {
+		t.Fatalf("with no presence key last heard is %v, want last_seen %v", m.lastHeard, seen)
+	}
+	at := now.Add(-5 * time.Minute)
+	applyPresence(&m, nil, at)
+	if !m.lastHeard.Equal(at) {
+		t.Fatalf("with a presence key last heard is %v, want %v", m.lastHeard, at)
+	}
+}